INDEX

Explanations

elements related to numerical data or measurements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nahilalakip

-0.74

 pleaſure

-0.69

jsxFileName

-0.66

 ModelExpression

-0.63

 purpoſe

-0.63

RegressionTest

-0.62

 متعلقه

-0.61

 himſelf

-0.60

ghijkl

-0.60

 myſelf

-0.58

POSITIVE LOGITS

AnchorStyles

0.72

].[

0.53

InputBorder

0.52

ließlich

0.52

 BoxFit

0.52

Embeddable

0.51

 CURLOPT

0.50

 RestTemplate

0.49

 disponer

0.49

ην

0.49

Activations Density 0.182%

elements related to numerical data or measurements

No Comments

No Known Activations